offload-onboard

Onboard a repository to use Offload for parallel test execution on Modal. Detects test setup, creates config, Dockerfile, CI job, and optimizes performance.

Quality

61%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/offload-onboard/SKILL.md

Quality

Discovery

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong on specificity and distinctiveness, clearly naming the product (Offload/Modal) and listing concrete deliverables (config, Dockerfile, CI job). However, it lacks an explicit 'Use when...' clause which caps completeness, and the trigger terms lean heavily on product-specific jargon rather than natural user language like 'speed up tests' or 'parallelize CI'.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to set up Offload, parallelize tests on Modal, or speed up CI test execution.'

Include more natural trigger terms users might say, such as 'speed up tests', 'parallelize testing', 'CI/CD optimization', or 'test infrastructure setup'.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: detects test setup, creates config, Dockerfile, CI job, and optimizes performance. These are clear, actionable capabilities.	3 / 3
Completeness	Clearly answers 'what' (onboard a repo, detect test setup, create config/Dockerfile/CI job, optimize performance) but lacks an explicit 'Use when...' clause. The 'when' is only implied by the nature of the task description.	2 / 3
Trigger Term Quality	Includes some relevant keywords like 'parallel test execution', 'Modal', 'Dockerfile', 'CI job', and 'Offload', but misses common user-facing terms like 'speed up tests', 'test parallelism', 'CI/CD', or 'testing infrastructure'. 'Offload' and 'Modal' are product-specific terms that users may or may not naturally use.	2 / 3
Distinctiveness Conflict Risk	Very specific niche: onboarding repos to 'Offload' for parallel test execution on 'Modal'. The combination of product names and specific workflow makes it highly unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Implementation

55%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill excels at actionability and workflow clarity — it provides a thorough, well-sequenced onboarding procedure with concrete code, explicit validation gates, and clear error recovery paths. However, it is severely over-long for a SKILL.md, cramming configuration references, multi-language templates, CI setup for multiple platforms, and troubleshooting guides all into a single file. The lack of any bundle files for progressive disclosure means Claude must load ~400+ lines of context even for simple onboarding scenarios.

Suggestions

Extract the configuration reference (field descriptions), troubleshooting table, and Dockerfile templates into separate bundle files (e.g., CONFIG_REFERENCE.md, TROUBLESHOOTING.md, DOCKERFILES.md) and reference them from the main skill.

Remove explanatory text Claude already knows — e.g., what .gitignore vs .dockerignore does, how GitHub secrets work, what CI systems exist — and replace with terse directives.

Move the CI job templates (GitHub Actions YAML, notes for GitLab/Jenkins/CircleCI) into a separate CI_SETUP.md file, keeping only a brief reference in the main workflow.

Trim the configuration reference section; the TOML templates with comments are already self-documenting, making the separate field-by-field descriptions redundant.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~400+ lines. It over-explains many concepts Claude already knows (what CI systems are, how git secrets work, what .gitignore does vs .dockerignore), includes extensive inline configuration references that could be in a separate file, and repeats information (e.g., rsync requirement mentioned in prerequisites and Dockerfile). The troubleshooting table, configuration reference, and summary table all add significant token cost that could be offloaded to reference files.	1 / 3
Actionability	The skill provides fully executable code blocks throughout — complete Dockerfiles, TOML configs, shell scripts, CI YAML, and specific CLI commands. Every step has concrete, copy-paste-ready examples with clear placeholders marked in angle brackets, and the troubleshooting table maps specific symptoms to specific fixes.	3 / 3
Workflow Clarity	The multi-step workflow is clearly sequenced with numbered steps, explicit validation checkpoints (offload collect before execution, baseline comparison before optimization, re-run after fixes), feedback loops (iterate until pass/fail counts match baseline, repeat vitest dedup until collect succeeds), and clear gate conditions (do not proceed until prerequisites confirmed, do not proceed until collect succeeds). The skip conditions for optional steps are also well-defined.	3 / 3
Progressive Disclosure	The entire skill is a monolithic wall of text with no bundle files to offload content to. The inline configuration reference, troubleshooting table, CI templates for multiple systems, Dockerfile templates for multiple languages, and the summary table could all be separate referenced files. There's one mention of 'see the Offload README' but no actual bundle structure to support progressive disclosure.	1 / 3
	Total	8 / 12 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (571 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: imbue-ai/offload
Commit: 7862a3c

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.